Packet flow tracing in a parallel processor complex

Abstract

In one example implementation, a computer-implemented method includes receiving, at a parallel processor complex, a task to be executed by the parallel processor complex. The parallel processor complex includes a trace processor and a plurality of task execution processors, each of the plurality of task execution processors having a plurality of trace buffers associated exclusively therewith. The method further includes creating, by the trace processor, a trace entry by allocating an element from a shared queue. The method further includes loading, by the trace processor, the trace entry into a common trace buffer. The method further includes loading, by the trace processor, the trace entry into one of the plurality of trace buffers based at least in part on an interface identifier and a queue pair index record. The interface identifier identifies the one of the plurality of task execution processors with which the trace entry is associated.

What is claimed is: 
     
       1. A system for packet flow tracing in a parallel processor complex, the system comprising:
 a memory comprising computer readable instructions; and 
 a processing device for executing the computer readable instructions for performing a method, the method comprising:
 receiving, at the parallel processor complex, a task to be executed by the parallel processor complex, wherein the parallel processor complex comprises a trace processor and a plurality of task execution processors, each of the plurality of task execution processors having a plurality of trace buffers associated exclusively therewith; 
 creating, by the trace processor, a trace entry by allocating an element from a shared queue; 
 loading, by the trace processor, the trace entry into a common trace buffer; and 
 loading, by the trace processor, the trace entry into one of the plurality of trace buffers based at least in part on an interface identifier and a queue pair index record, the interface identifier identifying the one of the plurality of task execution processors with which the trace entry is associated. 
 
 
     
     
       2. The system of  claim 1 , wherein the element uniquely identifies a host interface and a queue pair used for the element. 
     
     
       3. The system of  claim 1 , wherein the trace entry comprises a header. 
     
     
       4. The system of  claim 3 , wherein the header comprises a processor identifier, at interface identifier, a queue pair index, a tag, a timestamp, and unique data. 
     
     
       5. The system of  claim 4 , wherein the processor identifier is a unique identifier of a processor in the parallel processor complex, the interface identifier is a unique identifier assigned to a host interface of a particular processor in the parallel processor complex, the queue pair index is an index of the queue pair used to send a data stream, the tag identifies a specific trace point, the timestamp is a time when the trace entry was created using a timer common to the plurality of task execution processors, and the unique data is data associated with the tag. 
     
     
       6. The system of  claim 1 , wherein the trace processor uses the interface identifier and the queue pair index record to load the trace entry into the common trace buffer. 
     
     
       7. The system of  claim 1 , wherein the queue pair index record indicates to which of the plurality of trace buffers to load the trace entry. 
     
     
       8. A computer program product for packet flow tracing in a parallel processor complex, the computer program product comprising:
 a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing device to cause the processing device to perform a method comprising:
 receiving, at the parallel processor complex, a task to be executed by the parallel processor complex, wherein the parallel processor complex comprises a trace processor and a plurality of task execution processors, each of the plurality of task execution processors having a plurality of trace buffers associated exclusively therewith; 
 creating, by the trace processor, a trace entry by allocating an element from a shared queue; 
 loading, by the trace processor, the trace entry into a common trace buffer; and 
 loading, by the trace processor, the trace entry into one of the plurality of trace buffers based at least in part on an interface identifier and a queue pair index record, the interface identifier identifying the one of the plurality of task execution processors with which the trace entry is associated. 
 
 
     
     
       9. The computer program product of  claim 8 , wherein the element uniquely identifies a host interface and a queue pair used for the element. 
     
     
       10. The computer program product of  claim 8 , wherein the trace entry comprises a header. 
     
     
       11. The computer program product of  claim 10 , wherein the header comprises a processor identifier, at interface identifier, a queue pair index, a tag, a timestamp, and unique data. 
     
     
       12. The computer program product of  claim 11 , wherein the processor identifier is a unique identifier of a processor in the parallel processor complex, the interface identifier is a unique identifier assigned to a host interface of a particular processor in the parallel processor complex, the queue pair index is an index of the queue pair used to send a data stream, the tag identifies a specific trace point, the timestamp is a time when the trace entry was created using a timer common to the plurality of task execution processors, and the unique data is data associated with the tag. 
     
     
       13. The computer program product of  claim 8 , wherein the trace processor uses the interface identifier and the queue pair index record to load the trace entry into the common trace buffer. 
     
     
       14. The computer program product of  claim 8 , wherein the queue pair index record indicates to which of the plurality of trace buffers to load the trace entry.